Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 194 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6458. Min Act: 0.0000

Data Index: 103612 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6089. Min Act: -0.0000

Data Index: 143807 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5898. Min Act: -0.0000

Data Index: 324970 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5543. Min Act: 0.0002

Data Index: 1272940 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1232913 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5539. Min Act: 0.0001

Data Index: 147896 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5327. Min Act: 0.0001

Data Index: 929484 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5421. Min Act: -0.0000

Data Index: 188275 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5588. Min Act: 0.0000

Data Index: 329531 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5226. Min Act: 0.0002

Data Index: 1164383 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5221. Min Act: -0.0000

Data Index: 458262 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5377. Min Act: 0.0001

Data Index: 602762 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5025. Min Act: 0.0001

Data Index: 1205580 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4896. Min Act: 0.0001

Data Index: 542336 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1202414 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4952. Min Act: -0.0000

Data Index: 697535 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4941. Min Act: -0.0000

Data Index: 276426 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4748. Min Act: 0.0001

Data Index: 132502 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4758. Min Act: 0.0002

Data Index: 1099438 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4839. Min Act: -0.0000

Data Index: 33750 (C4 (Web Text))

Max Activating Token Index: 50